Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to appropriateness and relevance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĤÑĮ
    -0.17
    assage
    -0.17
     наÑĩала
    -0.16
    swick
    -0.16
    ertoire
    -0.16
    olley
    -0.15
    utow
    -0.15
    /bower
    -0.14
    deen
    -0.14
    _LL
    -0.14
    POSITIVE LOGITS
    astr
    0.16
     Campos
    0.15
    atis
    0.15
     Turner
    0.15
     McB
    0.14
    IED
    0.14
    ied
    0.14
    akan
    0.14
    çŃĴ
    0.14
     jun
    0.14
    Act Density 0.103%

    No Known Activations